blocks|key|1511043|text|如果这样做有帮助，可以用以下方法对模型进行腌制：|type|unstyled|depth|inlineStyleRanges|entityRanges|data|1511044|import+pickle
pickle.dump(grid_svm,+open('svm_sentiment_analyzer.pkl',+'wb'))|code-block|syntax|javascript|1511045|加载模型并进行预测|1511046|svm_detector_reloaded+=+pickle.load(open('svm_sentiment_analyzer.pkl',+'rb'))
print(svm_detector_reloaded.predict_proba(["Today+is+an+awesome+day"])[0])|1511047|在完成重新运行它的代码并在一只熊猫sents+DataFrame上训练模型之后，我返回了两个可能性。|offset|length|style|CODE|1511048|grid_svm.fit(sents.Sentence.values,+sents.Positive.values)|1511049|关于模型序列化的最佳实践(例如使用joblib)可以在persistence.html上找到|1511050|entityMap|0|LINK|mutability|MUTABLE|url|https://scikit-learn.org/stable/modules/model_persistence.html^0|0|0|0|0|H|5|0|0|H|6|R|G|0|0^^$0|@$1|2|3|4|5|6|7|12|8|@]|9|@]|A|$]]|$1|B|3|C|5|D|7|13|8|@]|9|@]|A|$E|F]]|$1|G|3|H|5|6|7|14|8|@]|9|@]|A|$]]|$1|I|3|J|5|D|7|15|8|@]|9|@]|A|$E|F]]|$1|K|3|L|5|6|7|16|8|@$M|17|N|18|O|P]]|9|@]|A|$]]|$1|Q|3|R|5|D|7|19|8|@]|9|@]|A|$E|F]]|$1|S|3|T|5|6|7|1A|8|@$M|1B|N|1C|O|P]]|9|@$M|1D|N|1E|1|1F]]|A|$]]|$1|U|3|-4|5|6|7|1G|8|@]|9|@]|A|$]]]|V|$W|$5|X|Y|Z|A|$10|11]]]]

If that can help, pickling the model with with:

<pre><code>import pickle
pickle.dump(grid_svm, open('svm_sentiment_analyzer.pkl', 'wb'))
</code></pre>

and loading the model and predicting with 

<pre><code>svm_detector_reloaded = pickle.load(open('svm_sentiment_analyzer.pkl', 'rb'))
print(svm_detector_reloaded.predict_proba(["Today is an awesome day"])[0])
</code></pre>

returned me two probabilities fine, after working on your code to rerun it and training the model on a pandas <code>sents</code> DataFrame with 

<pre><code>grid_svm.fit(sents.Sentence.values, sents.Positive.values)
</code></pre>

Best practices (e.g. using <code>joblib</code>) on model serialization can be found at <a href="https://scikit-learn.org/stable/modules/model_persistence.html" rel="nofollow noreferrer">https://scikit-learn.org/stable/modules/model_persistence.html</a>

blocks|key|1511075|text|您可以使用CallibratedClassifierCV进行概率分数输出。|type|unstyled|depth|inlineStyleRanges|entityRanges|data|1511076|from+sklearn.calibration+import+CalibratedClassifierCV

model_svc+=+LinearSVC()
model+=+CalibratedClassifierCV(model_svc)+
model.fit(X_train,+y_train)|code-block|syntax|javascript|1511077|使用泡菜保存模型。|1511078|import+pickle
filename+=+'linearSVC.sav'
pickle.dump(model,+open(filename,+'wb'))|1511079|基于pickle.load的负载模型。|1511080|model+=+pickle.load(open(filename,+'rb'))|offset|length|style|CODE|1511081|现在开始预测。|1511082|pred_class+=+model.predict(pred)
probability+=+model.predict_proba(pred)|1511083|entityMap^0|0|0|0|0|0|0|15|0|0|0^^$0|@$1|2|3|4|5|6|7|Y|8|@]|9|@]|A|$]]|$1|B|3|C|5|D|7|Z|8|@]|9|@]|A|$E|F]]|$1|G|3|H|5|6|7|10|8|@]|9|@]|A|$]]|$1|I|3|J|5|D|7|11|8|@]|9|@]|A|$E|F]]|$1|K|3|L|5|6|7|12|8|@]|9|@]|A|$]]|$1|M|3|N|5|6|7|13|8|@$O|14|P|15|Q|R]]|9|@]|A|$]]|$1|S|3|T|5|6|7|16|8|@]|9|@]|A|$]]|$1|U|3|V|5|D|7|17|8|@]|9|@]|A|$E|F]]|$1|W|3|-4|5|6|7|18|8|@]|9|@]|A|$]]]|X|$]]

You can use CallibratedClassifierCV for probability score output.

<pre><code>from sklearn.calibration import CalibratedClassifierCV

model_svc = LinearSVC()
model = CalibratedClassifierCV(model_svc) 
model.fit(X_train, y_train)
</code></pre>

Save model using pickle.

<pre><code>import pickle
filename = 'linearSVC.sav'
pickle.dump(model, open(filename, 'wb'))
</code></pre>

Load model using pickle.load.

<code>model = pickle.load(open(filename, 'rb'))</code>

Now start prediction.

<pre><code>pred_class = model.predict(pred)
probability = model.predict_proba(pred)
</code></pre>

blocks|key|1364351|text|用途：SVM(probability=True)|type|unstyled|depth|inlineStyleRanges|offset|length|style|CODE|entityRanges|data|1364352|或|1364353|grid_svm+=+GridSearchCV(
++++probability=True
++++pipeline_svm,
++++param_grid=param_svm,
++++refit=True,
++++n_jobs=-1,+
++++scoring='accuracy',
++++cv=StratifiedKFold(label_train,+n_folds=5),)|code-block|syntax|javascript|1364354|entityMap^0|3|L|0|0|0^^$0|@$1|2|3|4|5|6|7|O|8|@$9|P|A|Q|B|C]]|D|@]|E|$]]|$1|F|3|G|5|6|7|R|8|@]|D|@]|E|$]]|$1|H|3|I|5|J|7|S|8|@]|D|@]|E|$K|L]]|$1|M|3|-4|5|6|7|T|8|@]|D|@]|E|$]]]|N|$]]

Use: <code>SVM(probability=True)</code>

or 

<pre><code>grid_svm = GridSearchCV(
 probability=True
 pipeline_svm,
 param_grid=param_svm,
 refit=True,
 n_jobs=-1, 
 scoring='accuracy',
 cv=StratifiedKFold(label_train, n_folds=5),)
</code></pre>

blocks|key|1364366|text|使用predprobs函数计算auc(y_true，+y_score+)中要求的分数或概率/分数，问题在于y_score。您可以将其转换为如下代码行所示|type|unstyled|depth|inlineStyleRanges|offset|length|style|BOLD|entityRanges|data|1364367|#+Classifier+-+Algorithm+-+SVM
#+fit+the+training+dataset+on+the+classifier
SVM+=+svm.SVC(C=1.0,+kernel='linear',+degree=3,+gamma='auto',probability=True)
SVM.fit(Train_X_Tfidf,Train_Y)
#+predict+the+labels+on+validation+dataset
predictions_SVM+=+SVM.predict(Test_X_Tfidf)
#+Use+accuracy_score+function+to+get+the+accuracy
**print("SVM+Accuracy+Score+->+",accuracy_score(predictions_SVM,+Test_Y))**

probs+=+SVM.**predict_proba**(Test_X_Tfidf)
preds+=+probs[:,1]
fpr,+tpr,+threshold+=+**roc_curve(Test_Y,+preds)**
**print("SVM+Area+under+curve+->+",auc(fpr,+tpr))**|code-block|syntax|javascript|1364368|查看accuracy_score和auc()之间的差异，您需要预测的分数。|1364369|entityMap^0|Q|9|0|0|0^^$0|@$1|2|3|4|5|6|7|O|8|@$9|P|A|Q|B|C]]|D|@]|E|$]]|$1|F|3|G|5|H|7|R|8|@]|D|@]|E|$I|J]]|$1|K|3|L|5|6|7|S|8|@]|D|@]|E|$]]|$1|M|3|-4|5|6|7|T|8|@]|D|@]|E|$]]]|N|$]]

Use the predprobs function to calculate the scores or probabilities/scores as asked in the auc(y_true, y_score), the issue is because of y_score.
you can convert it as shown in the following line of code
<pre><code># Classifier - Algorithm - SVM
# fit the training dataset on the classifier
SVM = svm.SVC(C=1.0, kernel='linear', degree=3, gamma='auto',probability=True)
SVM.fit(Train_X_Tfidf,Train_Y)
# predict the labels on validation dataset
predictions_SVM = SVM.predict(Test_X_Tfidf)
# Use accuracy_score function to get the accuracy
**print(&quot;SVM Accuracy Score -&gt; &quot;,accuracy_score(predictions_SVM, Test_Y))**

probs = SVM.**predict_proba**(Test_X_Tfidf)
preds = probs[:,1]
fpr, tpr, threshold = **roc_curve(Test_Y, preds)**
**print(&quot;SVM Area under curve -&gt; &quot;,auc(fpr, tpr))**
</code></pre>
see the difference between the accuracy_score and the auc(), you need the scores of predictions.

blocks|key|1364381|text|添加(probability=True)时，根据上面的建议初始化分类器，解决了我的错误：|type|unstyled|depth|inlineStyleRanges|entityRanges|data|1364382|clf+=+SVC(kernel='rbf',+C=1e9,+gamma=1e-07,+probability=True).fit(xtrain,ytrain)|code-block|syntax|javascript|1364383|entityMap^0|0|0^^$0|@$1|2|3|4|5|6|7|I|8|@]|9|@]|A|$]]|$1|B|3|C|5|D|7|J|8|@]|9|@]|A|$E|F]]|$1|G|3|-4|5|6|7|K|8|@]|9|@]|A|$]]]|H|$]]

Adding (probability=True) while initializing the classifier as someone above suggested, resolved my error:
<pre><code>clf = SVC(kernel='rbf', C=1e9, gamma=1e-07, probability=True).fit(xtrain,ytrain)
</code></pre>

I built sentiment analyzer using SVM classifier. I trained model with probability=True and it can give me probability. But when I pickled my model and load it again later, the probability doesn't work anymore.

The model:

<pre><code>from sklearn.svm import SVC, LinearSVC
pipeline_svm = Pipeline([
 ('bow', CountVectorizer()),
 ('tfidf', TfidfTransformer()),
 ('classifier', SVC(probability=True)),])

# pipeline parameters to automatically explore and tune
param_svm = [
 {'classifier__C': [1, 10, 100, 1000], 'classifier__kernel': ['linear']},
 {'classifier__C': [1, 10, 100, 1000], 'classifier__gamma': [0.001, 0.0001], 'classifier__kernel': ['rbf']},
]

grid_svm = GridSearchCV(
 pipeline_svm,
 param_grid=param_svm,
 refit=True,
 n_jobs=-1, 
 scoring='accuracy',
 cv=StratifiedKFold(label_train, n_folds=5),)

svm_detector_reloaded = cPickle.load(open('svm_sentiment_analyzer.pkl', 'rb'))
print(svm_detector_reloaded.predict([""""Today is awesome day"""])[0])
</code></pre>

Gives me: 

<blockquote>
 AttributeError: predict_proba is not available when probability=False
</blockquote>

Scikit learn SVC predict probability doesn't work as expected

翻译质量差，导致语言生硬或混乱。

没有提供实际的解决方法或示例。

解答不清晰，无法理解或解决问题。

页面排版不美观，阅读体验差。

文章

问答

视频

学习中心

腾讯云实验室

直播

竞赛

腾讯云代码分析专区

腾讯iOA零信任安全管理系统专区

腾讯云架构师技术同盟交流圈

腾讯云数据库专区

腾讯云顾问专区

腾讯云原生专区

腾讯混元专区

腾讯云TCE专区

腾讯云Lighthouse专区

腾讯云HAI专区

腾讯云Edgeone专区

腾讯云存储专区

腾讯云智能专区

腾讯轻联专区 

腾讯云开发专区

TAPD专区

腾讯轻量云游戏服专区

腾讯云最具价值专家

腾讯云架构师技术同盟

腾讯云创作之星

腾讯云开发者先锋

腾讯云代码助手

云原生构建

TAPD 敏捷项目管理

Cloud Studio

SDK中心

API中心

命令行工具

涵盖代码开发、场景应用、自动测试全流程，助你从零构建专属AI助手

一站式MCP教程库，解锁AI应用新玩法

利用SVM分类器建立了情感分析器。我用probability=True训练模型，它可以给我概率。但是，当我将我的模型腌制并在以后再次加载时，这个概率就不再起作用了。模式：from sklearn.svm import SVC, LinearSVCpipeline_svm = Pipeline([    ('bow', ...

问Scikit学习SVC预测概率不像预期的那样工作
EN

Stack Overflow用户

社区

活动

圈层

关于

腾讯云开发者

热门产品

热门推荐

更多推荐

问Scikit学习SVC预测概率不像预期的那样工作EN